steps:
  - input: "Provide Release version here"
    id: input-release-version
    fields:
      - text: "What is the release version?"
        key: release-version

  - group: "Build Python wheels"
    key: "build-wheels"
    steps:
      - label: "Build wheel - aarch64 - CUDA 12.9"
        depends_on: ~
        id: build-wheel-arm64-cuda-12-9
        agents:
          queue: arm64_cpu_queue_release
        commands:
          # #NOTE: torch_cuda_arch_list is derived from upstream PyTorch build files here:
          # https://github.com/pytorch/pytorch/blob/main/.ci/aarch64_linux/aarch64_ci_build.sh#L7
          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.9.1 --build-arg torch_cuda_arch_list='8.7 8.9 9.0 10.0+PTX 12.0' --tag vllm-ci:build-image --target build --progress plain -f docker/Dockerfile ."
          - "mkdir artifacts"
          - "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'"
          - "bash .buildkite/scripts/upload-nightly-wheels.sh"
        env:
          DOCKER_BUILDKIT: "1"

      - label: "Build wheel - aarch64 - CUDA 13.0"
        depends_on: ~
        id: build-wheel-arm64-cuda-13-0
        agents:
          queue: arm64_cpu_queue_release
        commands:
          # #NOTE: torch_cuda_arch_list is derived from upstream PyTorch build files here:
          # https://github.com/pytorch/pytorch/blob/main/.ci/aarch64_linux/aarch64_ci_build.sh#L7
          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=13.0.1 --build-arg torch_cuda_arch_list='8.7 8.9 9.0 10.0+PTX 12.0' --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.1-devel-ubuntu22.04  --tag vllm-ci:build-image --target build --progress plain -f docker/Dockerfile ."
          - "mkdir artifacts"
          - "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'"
          - "bash .buildkite/scripts/upload-nightly-wheels.sh manylinux_2_35"
        env:
          DOCKER_BUILDKIT: "1"

      - label: "Build wheel - aarch64 - CPU"
        depends_on: ~
        id: build-wheel-arm64-cpu
        agents:
          queue: arm64_cpu_queue_release
        commands:
          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg GIT_REPO_CHECK=1 --build-arg VLLM_BUILD_ACL=ON --tag vllm-ci:build-image --target vllm-build --progress plain -f docker/Dockerfile.cpu ."
          - "mkdir artifacts"
          - "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'"
          - "bash .buildkite/scripts/upload-nightly-wheels.sh manylinux_2_35"
        env:
          DOCKER_BUILDKIT: "1"

      - label: "Build wheel - x86_64 - CUDA 12.9"
        depends_on: ~
        id: build-wheel-x86-cuda-12-9
        agents:
          queue: cpu_queue_release
        commands:
          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.9.1 --tag vllm-ci:build-image --target build --progress plain -f docker/Dockerfile ."
          - "mkdir artifacts"
          - "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'"
          - "bash .buildkite/scripts/upload-nightly-wheels.sh manylinux_2_31"
        env:
          DOCKER_BUILDKIT: "1"

      - label: "Build wheel - x86_64 - CUDA 13.0"
        depends_on: ~
        id: build-wheel-x86-cuda-13-0
        agents:
          queue: cpu_queue_release
        commands:
          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=13.0.1 --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.1-devel-ubuntu22.04 --tag vllm-ci:build-image --target build --progress plain -f docker/Dockerfile ."
          - "mkdir artifacts"
          - "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'"
          - "bash .buildkite/scripts/upload-nightly-wheels.sh manylinux_2_35"
        env:
          DOCKER_BUILDKIT: "1"

      - label: "Build wheel - x86_64 - CPU"
        depends_on: ~
        id: build-wheel-x86-cpu
        agents:
          queue: cpu_queue_release
        commands:
          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg GIT_REPO_CHECK=1 --build-arg VLLM_CPU_X86=true --tag vllm-ci:build-image --target vllm-build --progress plain -f docker/Dockerfile.cpu ."
          - "mkdir artifacts"
          - "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'"
          - "bash .buildkite/scripts/upload-nightly-wheels.sh manylinux_2_35"
        env:
          DOCKER_BUILDKIT: "1"

  - label: "Generate and upload wheel indices"
    depends_on: "build-wheels"
    allow_dependency_failure: true
    agents:
      queue: cpu_queue_release
    commands:
      - "bash .buildkite/scripts/generate-and-upload-nightly-index.sh"

  - group: "Build release Docker images"
    key: "build-release-images"
    steps:
      - label: "Build release image - x86_64 - CUDA 12.9"
        depends_on: ~
        id: build-release-image-x86
        agents:
          queue: cpu_queue_release
        commands:
          - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.9.1 --build-arg FLASHINFER_AOT_COMPILE=true --build-arg INSTALL_KV_CONNECTORS=true --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m) --target vllm-openai --progress plain -f docker/Dockerfile ."
          - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)"
          # re-tag to default image tag and push, just in case arm64 build fails
          - "docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m) public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT"
          - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT"

      - label: "Build release image - aarch64 - CUDA 12.9"
        depends_on: ~
        id: build-release-image-arm64
        agents:
          queue: arm64_cpu_queue_release
        commands:
          - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.9.1 --build-arg FLASHINFER_AOT_COMPILE=true --build-arg torch_cuda_arch_list='8.7 8.9 9.0 10.0+PTX 12.0' --build-arg INSTALL_KV_CONNECTORS=true --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m) --target vllm-openai --progress plain -f docker/Dockerfile ."
          - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)"

      - label: "Build release image - x86_64 - CUDA 13.0"
        depends_on: ~
        id: build-release-image-x86-cuda-13-0
        agents:
          queue: cpu_queue_release
        commands:
          - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=13.0.1 --build-arg INSTALL_KV_CONNECTORS=true --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.1-devel-ubuntu22.04 --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130 --target vllm-openai --progress plain -f docker/Dockerfile ."
          - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130"
          # re-tag to default image tag and push, just in case arm64 build fails
          - "docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-cu130"
          - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-cu130"

      - label: "Build release image - aarch64 - CUDA 13.0"
        depends_on: ~
        id: build-release-image-arm64-cuda-13-0
        agents:
          queue: arm64_cpu_queue_release
        commands:
          - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
          # compute capability 12.0 for RTX-50 series / RTX PRO 6000 Blackwell, 12.1 for DGX Spark
          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=13.0.1 --build-arg torch_cuda_arch_list='8.7 8.9 9.0 10.0+PTX 12.0 12.1' --build-arg INSTALL_KV_CONNECTORS=true --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.1-devel-ubuntu22.04 --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130 --target vllm-openai --progress plain -f docker/Dockerfile ."
          - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130"

      - label: "Build release image - x86_64 - CUDA 12.9 - Ubuntu 24.04"
        depends_on: ~
        id: build-release-image-x86-ubuntu2404
        agents:
          queue: cpu_queue_release
        commands:
          - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.9.1 --build-arg UBUNTU_VERSION=24.04 --build-arg GDRCOPY_OS_VERSION=Ubuntu24_04 --build-arg FLASHINFER_AOT_COMPILE=true --build-arg torch_cuda_arch_list='8.7 8.9 9.0 10.0+PTX 12.0' --build-arg INSTALL_KV_CONNECTORS=true --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-ubuntu2404 --target vllm-openai --progress plain -f docker/Dockerfile ."
          - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-ubuntu2404"
          - "docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-ubuntu2404 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-ubuntu2404"
          - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-ubuntu2404"

      - label: "Build release image - aarch64 - CUDA 12.9 - Ubuntu 24.04"
        depends_on: ~
        id: build-release-image-arm64-ubuntu2404
        agents:
          queue: arm64_cpu_queue_release
        commands:
          - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.9.1 --build-arg UBUNTU_VERSION=24.04 --build-arg GDRCOPY_OS_VERSION=Ubuntu24_04 --build-arg FLASHINFER_AOT_COMPILE=true --build-arg torch_cuda_arch_list='8.7 8.9 9.0 10.0+PTX 12.0' --build-arg INSTALL_KV_CONNECTORS=true --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-ubuntu2404 --target vllm-openai --progress plain -f docker/Dockerfile ."
          - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-ubuntu2404"

      - label: "Build release image - x86_64 - CUDA 13.0 - Ubuntu 24.04"
        depends_on: ~
        id: build-release-image-x86-cuda-13-0-ubuntu2404
        agents:
          queue: cpu_queue_release
        commands:
          - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=13.0.1 --build-arg UBUNTU_VERSION=24.04 --build-arg GDRCOPY_OS_VERSION=Ubuntu24_04 --build-arg FLASHINFER_AOT_COMPILE=true --build-arg torch_cuda_arch_list='8.7 8.9 9.0 10.0+PTX 12.0 12.1' --build-arg INSTALL_KV_CONNECTORS=true --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.1-devel-ubuntu24.04 --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130-ubuntu2404 --target vllm-openai --progress plain -f docker/Dockerfile ."
          - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130-ubuntu2404"
          - "docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130-ubuntu2404 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-cu130-ubuntu2404"
          - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-cu130-ubuntu2404"

      - label: "Build release image - aarch64 - CUDA 13.0 - Ubuntu 24.04"
        depends_on: ~
        id: build-release-image-arm64-cuda-13-0-ubuntu2404
        agents:
          queue: arm64_cpu_queue_release
        commands:
          - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=13.0.1 --build-arg UBUNTU_VERSION=24.04 --build-arg GDRCOPY_OS_VERSION=Ubuntu24_04 --build-arg FLASHINFER_AOT_COMPILE=true --build-arg torch_cuda_arch_list='8.7 8.9 9.0 10.0+PTX 12.0 12.1' --build-arg INSTALL_KV_CONNECTORS=true --build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.1-devel-ubuntu24.04 --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130-ubuntu2404 --target vllm-openai --progress plain -f docker/Dockerfile ."
          - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-$(uname -m)-cu130-ubuntu2404"

      - block: "Build release image for x86_64 CPU"
        key: block-cpu-release-image-build
        depends_on: ~

      - label: "Build release image - x86_64 - CPU"
        depends_on:
          - block-cpu-release-image-build
          - input-release-version
        agents:
          queue: cpu_queue_release
        commands:
          - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg GIT_REPO_CHECK=1 --build-arg VLLM_CPU_X86=true --tag public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:$(buildkite-agent meta-data get release-version) --tag public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:latest --progress plain --target vllm-openai -f docker/Dockerfile.cpu ."
          - "docker push public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:latest"
          - "docker push public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:$(buildkite-agent meta-data get release-version)"
        env:
          DOCKER_BUILDKIT: "1"

      - block: "Build release image for arm64 CPU"
        key: block-arm64-cpu-release-image-build
        depends_on: ~

      - label: "Build release image - arm64 - CPU"
        depends_on: 
          - block-arm64-cpu-release-image-build
          - input-release-version
        agents:
          queue: arm64_cpu_queue_release
        commands:
          - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
          - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg GIT_REPO_CHECK=1 --tag public.ecr.aws/q9t5s3a7/vllm-arm64-cpu-release-repo:$(buildkite-agent meta-data get release-version) --tag public.ecr.aws/q9t5s3a7/vllm-arm64-cpu-release-repo:latest --progress plain --target vllm-openai -f docker/Dockerfile.cpu ."
          - "docker push public.ecr.aws/q9t5s3a7/vllm-arm64-cpu-release-repo:latest"
          - "docker push public.ecr.aws/q9t5s3a7/vllm-arm64-cpu-release-repo:$(buildkite-agent meta-data get release-version)"
        env:
          DOCKER_BUILDKIT: "1"

  - group: "Publish release images"
    key: "publish-release-images"
    steps:
      - label: "Create multi-arch manifest - CUDA 12.9"
        depends_on:
          - build-release-image-x86
          - build-release-image-arm64
        id: create-multi-arch-manifest
        agents:
          queue: small_cpu_queue_release
        commands:
          - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
          - "docker manifest create public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-x86_64 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-aarch64 --amend"
          - "docker manifest push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT"

      - label: "Annotate release workflow - CUDA 12.9"
        depends_on:
          - create-multi-arch-manifest
        id: annotate-release-workflow
        agents:
          queue: small_cpu_queue_release
        commands:
          - "bash .buildkite/scripts/annotate-release.sh"

      - label: "Create multi-arch manifest - CUDA 13.0"
        depends_on:
          - build-release-image-x86-cuda-13-0
          - build-release-image-arm64-cuda-13-0
        id: create-multi-arch-manifest-cuda-13-0
        agents:
          queue: small_cpu_queue_release
        commands:
          - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
          - "docker manifest create public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-cu130 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-x86_64-cu130 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-aarch64-cu130 --amend"
          - "docker manifest push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-cu130"

      - label: "Create multi-arch manifest - CUDA 12.9 - Ubuntu 24.04"
        depends_on:
          - build-release-image-x86-ubuntu2404
          - build-release-image-arm64-ubuntu2404
        id: create-multi-arch-manifest-ubuntu2404
        agents:
          queue: small_cpu_queue_release
        commands:
          - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
          - "docker manifest create public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-ubuntu2404 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-x86_64-ubuntu2404 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-aarch64-ubuntu2404 --amend"
          - "docker manifest push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-ubuntu2404"

      - label: "Create multi-arch manifest - CUDA 13.0 - Ubuntu 24.04"
        depends_on:
          - build-release-image-x86-cuda-13-0-ubuntu2404
          - build-release-image-arm64-cuda-13-0-ubuntu2404
        id: create-multi-arch-manifest-cuda-13-0-ubuntu2404
        agents:
          queue: small_cpu_queue_release
        commands:
          - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
          - "docker manifest create public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-cu130-ubuntu2404 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-x86_64-cu130-ubuntu2404 public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-aarch64-cu130-ubuntu2404 --amend"
          - "docker manifest push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-cu130-ubuntu2404"

      - label: "Publish nightly multi-arch image to DockerHub"
        depends_on:
          - create-multi-arch-manifest
        if: build.env("NIGHTLY") == "1"
        agents:
          queue: small_cpu_queue_release
        commands:
          - "bash .buildkite/scripts/push-nightly-builds.sh"
          # Clean up old nightly builds (keep only last 14)
          - "bash .buildkite/scripts/cleanup-nightly-builds.sh"
        plugins:
          - docker-login#v3.0.0:
              username: vllmbot
              password-env: DOCKERHUB_TOKEN
        env:
          DOCKER_BUILDKIT: "1"
          DOCKERHUB_USERNAME: "vllmbot"

      - label: "Publish nightly multi-arch image to DockerHub - CUDA 13.0"
        depends_on:
          - create-multi-arch-manifest-cuda-13-0
        if: build.env("NIGHTLY") == "1"
        agents:
          queue: small_cpu_queue_release
        commands:
          - "bash .buildkite/scripts/push-nightly-builds.sh cu130"
          # Clean up old nightly builds (keep only last 14)
          - "bash .buildkite/scripts/cleanup-nightly-builds.sh cu130-nightly-"
        plugins:
          - docker-login#v3.0.0:
              username: vllmbot
              password-env: DOCKERHUB_TOKEN
        env:
          DOCKER_BUILDKIT: "1"
          DOCKERHUB_USERNAME: "vllmbot"

  - group: "Publish wheels"
    key: "publish-wheels"
    steps:
      - block: "Confirm update release wheels to PyPI (experimental, use with caution)?"
        key: block-upload-release-wheels
        depends_on:
          - input-release-version
          - build-wheels

      - label: "Upload release wheels to PyPI"
        depends_on:
          - block-upload-release-wheels
        id: upload-release-wheels
        agents:
          queue: small_cpu_queue_release
        commands:
          - "bash .buildkite/scripts/upload-release-wheels-pypi.sh"

  # =============================================================================
  # ROCm Release Pipeline (x86_64 only)
  # =============================================================================
  #
  # vLLM version is determined by the Buildkite checkout (like CUDA pipeline).
  # To build a specific version, trigger the build from that branch/tag.
  #
  # Environment variables for ROCm builds (set via Buildkite UI or schedule):
  #
  # Note: ROCm version is determined by BASE_IMAGE in docker/Dockerfile.rocm_base
  #
  # =============================================================================

  # ROCm Job 1: Build ROCm Base Wheels (with S3 caching)
  - label: ":rocm: Build ROCm Base Image & Wheels"
    id: build-rocm-base-wheels
    depends_on: ~
    agents:
      queue: cpu_queue_release
    commands:
      - |
        set -euo pipefail

        # Generate cache key
        CACHE_KEY=$$(.buildkite/scripts/cache-rocm-base-wheels.sh key)
        ECR_CACHE_TAG="public.ecr.aws/q9t5s3a7/vllm-release-repo:$${CACHE_KEY}-rocm-base"

        echo "========================================"
        echo "ROCm Base Build Configuration"
        echo "========================================"
        echo "  CACHE_KEY: $${CACHE_KEY}"
        echo "  ECR_CACHE_TAG: $${ECR_CACHE_TAG}"
        echo "========================================"
        
        # Login to ECR
        aws ecr-public get-login-password --region us-east-1 | \
          docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7
        
        IMAGE_EXISTS=false
        WHEELS_EXIST=false
        
        # Check ECR for Docker image

        if docker manifest inspect "$${ECR_CACHE_TAG}" > /dev/null 2>&1; then
          IMAGE_EXISTS=true
          echo "ECR image cache HIT"
        fi
        
        # Check S3 for wheels
        WHEEL_CACHE_STATUS=$(.buildkite/scripts/cache-rocm-base-wheels.sh check)
        if [ "$${WHEEL_CACHE_STATUS}" = "hit" ]; then
          WHEELS_EXIST=true
          echo "S3 wheels cache HIT"
        fi

        
        # Scenario 1: Both cached (best case)
        if [ "$${IMAGE_EXISTS}" = "true" ] && [ "$${WHEELS_EXIST}" = "true" ]; then
          echo ""
          echo "FULL CACHE HIT - Reusing both image and wheels"
          echo ""

          # Download wheels
          .buildkite/scripts/cache-rocm-base-wheels.sh download
          
          # Save ECR tag for downstream jobs
          buildkite-agent meta-data set "rocm-base-image-tag" "$${ECR_CACHE_TAG}"
          
        # Scenario 2: Full rebuild needed
        else
          echo ""
          echo " CACHE MISS - Building from scratch..."
          echo ""
          
          # Build full base image and push to ECR
          DOCKER_BUILDKIT=1 docker buildx build \
            --file docker/Dockerfile.rocm_base \
            --tag "$${ECR_CACHE_TAG}" \
            --build-arg USE_SCCACHE=1 \
            --build-arg SCCACHE_BUCKET_NAME=vllm-build-sccache \
            --build-arg SCCACHE_REGION_NAME=us-west-2 \
            --build-arg SCCACHE_S3_NO_CREDENTIALS=0 \
            --push \
            .
          
          # Build wheel extraction stage
          DOCKER_BUILDKIT=1 docker buildx build \
            --file docker/Dockerfile.rocm_base \
            --tag rocm-base-debs:$${BUILDKITE_BUILD_NUMBER} \
            --target debs_wheel_release \
            --build-arg USE_SCCACHE=1 \
            --build-arg SCCACHE_BUCKET_NAME=vllm-build-sccache \
            --build-arg SCCACHE_REGION_NAME=us-west-2 \
            --build-arg SCCACHE_S3_NO_CREDENTIALS=0 \
            --load \
            .
          
          # Extract and upload wheels
          mkdir -p artifacts/rocm-base-wheels
          cid=$(docker create rocm-base-debs:$${BUILDKITE_BUILD_NUMBER})
          docker cp $${cid}:/app/debs/. artifacts/rocm-base-wheels/
          docker rm $${cid}
          
          .buildkite/scripts/cache-rocm-base-wheels.sh upload

          # Cache base docker image to ECR
          docker push "$${ECR_CACHE_TAG}"
          
          buildkite-agent meta-data set "rocm-base-image-tag" "$${ECR_CACHE_TAG}"
          
          echo ""
          echo " Build complete - Image and wheels cached"
        fi
        
    artifact_paths:
      - "artifacts/rocm-base-wheels/*.whl"
    env:
      DOCKER_BUILDKIT: "1"
      S3_BUCKET: "vllm-wheels"

  # ROCm Job 2: Build vLLM ROCm Wheel
  - label: ":python: Build vLLM ROCm Wheel - x86_64"
    id: build-rocm-vllm-wheel
    depends_on:
      - step: build-rocm-base-wheels
        allow_failure: false
    agents:
      queue: cpu_queue_release
    timeout_in_minutes: 180
    commands:
      # Download artifacts and prepare Docker image
      - |
        set -euo pipefail

        # Ensure git tags are up-to-date (Buildkite's default fetch doesn't update tags)
        # This fixes version detection when tags are moved/force-pushed
        echo "Fetching latest tags from origin..."
        git fetch --tags --force origin
        
        # Log tag information for debugging version detection
        echo "========================================"
        echo "Git Tag Verification"
        echo "========================================"
        echo "Current HEAD: $(git rev-parse HEAD)"
        echo "git describe --tags: $(git describe --tags 2>/dev/null || echo 'No tags found')"
        echo ""
        echo "Recent tags (pointing to commits near HEAD):"
        git tag -l --sort=-creatordate | head -5
        echo "setuptools_scm version detection:"
        pip install -q setuptools_scm 2>/dev/null || true
        python3 -c "import setuptools_scm; print('  Detected version:', setuptools_scm.get_version())" 2>/dev/null || echo "  (setuptools_scm not available in this environment)"
        echo "========================================"

        # Download wheel artifacts from current build
        echo "Downloading wheel artifacts from current build"
        buildkite-agent artifact download "artifacts/rocm-base-wheels/*.whl" .

        # Get ECR image tag from metadata (set by build-rocm-base-wheels)
        ECR_IMAGE_TAG="$$(buildkite-agent meta-data get rocm-base-image-tag 2>/dev/null || echo '')"
        if [ -z "$${ECR_IMAGE_TAG}" ]; then
          echo "ERROR: rocm-base-image-tag metadata not found"
          echo "This should have been set by the build-rocm-base-wheels job"
          exit 1
        fi
        
        echo "Pulling base Docker image from ECR: $${ECR_IMAGE_TAG}"
        
        # Login to ECR
        aws ecr-public get-login-password --region us-east-1 | \
          docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7
        
        # Pull base Docker image from ECR
        docker pull "$${ECR_IMAGE_TAG}"
        
        echo "Loaded base image: $${ECR_IMAGE_TAG}"
        
        # Prepare base wheels for Docker build context
        mkdir -p docker/context/base-wheels
        touch docker/context/base-wheels/.keep
        cp artifacts/rocm-base-wheels/*.whl docker/context/base-wheels/
        echo "Base wheels for vLLM build:"
        ls -lh docker/context/base-wheels/

        echo "========================================"
        echo "Building vLLM wheel with:"
        echo "  BUILDKITE_COMMIT: $${BUILDKITE_COMMIT}"
        echo "  BUILDKITE_BRANCH: $${BUILDKITE_BRANCH}"
        echo "  BASE_IMAGE: $${ECR_IMAGE_TAG}"
        echo "========================================"

        # Build vLLM wheel using local checkout (REMOTE_VLLM=0)
        DOCKER_BUILDKIT=1 docker build \
          --file docker/Dockerfile.rocm \
          --target export_vllm_wheel_release \
          --output type=local,dest=rocm-dist \
          --build-arg BASE_IMAGE="$${ECR_IMAGE_TAG}" \
          --build-arg REMOTE_VLLM=0 \
          --build-arg GIT_REPO_CHECK=1 \
          --build-arg USE_SCCACHE=1 \
          --build-arg SCCACHE_BUCKET_NAME=vllm-build-sccache \
          --build-arg SCCACHE_REGION_NAME=us-west-2 \
          --build-arg SCCACHE_S3_NO_CREDENTIALS=0 \
          .
        echo "Built vLLM wheel:"
        ls -lh rocm-dist/*.whl
        # Copy wheel to artifacts directory
        mkdir -p artifacts/rocm-vllm-wheel
        cp rocm-dist/*.whl artifacts/rocm-vllm-wheel/
        echo "Final vLLM wheel:"
        ls -lh artifacts/rocm-vllm-wheel/
    artifact_paths:
      - "artifacts/rocm-vllm-wheel/*.whl"
    env:
      DOCKER_BUILDKIT: "1"
      S3_BUCKET: "vllm-wheels"

  # ROCm Job 3: Upload Wheels to S3
  - label: ":s3: Upload ROCm Wheels to S3"
    id: upload-rocm-wheels
    depends_on:
      - step: build-rocm-vllm-wheel
        allow_failure: false
    agents:
      queue: cpu_queue_release
    timeout_in_minutes: 60
    commands:
      # Download all wheel artifacts and run upload
      - |
        set -euo pipefail

        # Download artifacts from current build
        echo "Downloading artifacts from current build"
        buildkite-agent artifact download "artifacts/rocm-base-wheels/*.whl" .
        buildkite-agent artifact download "artifacts/rocm-vllm-wheel/*.whl" .

        # Run upload script
        bash .buildkite/scripts/upload-rocm-wheels.sh
    env:
      DOCKER_BUILDKIT: "1"
      S3_BUCKET: "vllm-wheels"

  # ROCm Job 4: Annotate ROCm Wheel Release
  - label: ":memo: Annotate ROCm wheel release"
    id: annotate-rocm-release
    depends_on:
      - upload-rocm-wheels
    agents:
      queue: cpu_queue_release
    commands:
      - "bash .buildkite/scripts/annotate-rocm-release.sh"
    env:
      S3_BUCKET: "vllm-wheels"

  # ROCm Job 5: Generate Root Index for ROCm Wheels (for release only)
  # This is the job to create https://wheels.vllm.ai/rocm/ index allowing
  # users to install with `uv pip install vllm --extra-index-url https://wheels.vllm.ai/rocm/`
  - block: "Generate Root Index for ROCm Wheels for Release"
    key: block-generate-root-index-rocm-wheels
    depends_on: upload-rocm-wheels

  - label: ":package: Generate Root Index for ROCm Wheels for Release"
    depends_on: block-generate-root-index-rocm-wheels
    id: generate-root-index-rocm-wheels
    agents:
      queue: cpu_queue_release
    commands:
      - "bash tools/vllm-rocm/generate-rocm-wheels-root-index.sh"
    env:
      S3_BUCKET: "vllm-wheels"
      VARIANT: "rocm721"

  # ROCm Job 6: Build ROCm Release Docker Image
  - label: ":docker: Build release image - x86_64 - ROCm"
    id: build-rocm-release-image
    depends_on:
      - step: build-rocm-base-wheels
        allow_failure: false
    agents:
      queue: cpu_queue_release
    timeout_in_minutes: 60
    commands:
      - |
        set -euo pipefail
        
        # Login to ECR
        aws ecr-public get-login-password --region us-east-1 | \
          docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7
        
        # Get ECR image tag from metadata (set by build-rocm-base-wheels)
        ECR_IMAGE_TAG="$$(buildkite-agent meta-data get rocm-base-image-tag 2>/dev/null || echo '')"
        if [ -z "$${ECR_IMAGE_TAG}" ]; then
          echo "ERROR: rocm-base-image-tag metadata not found"
          echo "This should have been set by the build-rocm-base-wheels job"
          exit 1
        fi
        
        echo "Pulling base Docker image from ECR: $${ECR_IMAGE_TAG}"
        
        # Pull base Docker image from ECR
        docker pull "$${ECR_IMAGE_TAG}"
        
        echo "Loaded base image: $${ECR_IMAGE_TAG}"
        
        # Pass the base image ECR tag to downstream steps (nightly publish)
        buildkite-agent meta-data set "rocm-base-ecr-tag" "$${ECR_IMAGE_TAG}"
        
        echo "========================================"
        echo "Building vLLM ROCm release image with:"
        echo "  BASE_IMAGE: $${ECR_IMAGE_TAG}"
        echo "  BUILDKITE_COMMIT: $${BUILDKITE_COMMIT}"
        echo "========================================"
        
        # Build vLLM ROCm release image using cached base
        DOCKER_BUILDKIT=1 docker build \
          --build-arg max_jobs=16 \
          --build-arg BASE_IMAGE="$${ECR_IMAGE_TAG}" \
          --build-arg USE_SCCACHE=1 \
          --build-arg SCCACHE_BUCKET_NAME=vllm-build-sccache \
          --build-arg SCCACHE_REGION_NAME=us-west-2 \
          --build-arg SCCACHE_S3_NO_CREDENTIALS=0 \
          --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$${BUILDKITE_COMMIT}-rocm \
          --target vllm-openai \
          --progress plain \
          -f docker/Dockerfile.rocm .
        
        # Push to ECR
        docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$${BUILDKITE_COMMIT}-rocm
        
        echo ""
        echo " Successfully built and pushed ROCm release image"
        echo "   Image: public.ecr.aws/q9t5s3a7/vllm-release-repo:$${BUILDKITE_COMMIT}-rocm"
        echo ""
    env:
      DOCKER_BUILDKIT: "1"
      S3_BUCKET: "vllm-wheels"

  - label: "Publish nightly ROCm image to DockerHub"
    depends_on:
      - build-rocm-release-image
    if: build.env("NIGHTLY") == "1"
    agents:
      queue: small_cpu_queue_release
    commands:
      - "bash .buildkite/scripts/push-nightly-builds-rocm.sh"
      # Clean up old nightly builds (keep only last 14)
      - "bash .buildkite/scripts/cleanup-nightly-builds.sh nightly- vllm/vllm-openai-rocm"
      - "bash .buildkite/scripts/cleanup-nightly-builds.sh base-nightly- vllm/vllm-openai-rocm"
    plugins:
      - docker-login#v3.0.0:
          username: vllmbot
          password-env: DOCKERHUB_TOKEN
    env:
      DOCKER_BUILDKIT: "1"
      DOCKERHUB_USERNAME: "vllmbot"